{"id":"W2150856587","doi":"10.1093/bioinformatics/bth057","title":"Cluster Analyzer for Transcription Sites (CATS): a C++-based program for identifying clustered transcription factor binding sites","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"D-Wave Systems (Canada)","funders":"Howard Hughes Medical Institute","keywords":"Transcription factor; DNA binding site; Consensus sequence; Biology; Computational biology; Transcription (linguistics); Genome; Binding site; CATS; DNA; Genetics; DNA sequencing; Gene; Promoter; Computer science; Base sequence; Gene expression","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000190181,0.0002621611,0.0002212876,0.0001239622,0.0002186569,0.000180425,0.0002033676,0.0002487915,0.000005326824],"category_scores_gemma":[0.00004494133,0.0002545893,0.0003385733,0.0001079056,0.00004927463,0.00003139369,0.00002002512,0.00006642445,0.00000604654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007414843,"about_ca_system_score_gemma":0.0000931059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003907689,"about_ca_topic_score_gemma":0.0001062701,"domain_scores_codex":[0.9986554,0.00001250734,0.0005472469,0.0002418939,0.0001404502,0.0004024571],"domain_scores_gemma":[0.9992394,0.00001899943,0.0002134633,0.0002760543,0.0001557721,0.00009630322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002659114,0.0002065762,0.0002041627,0.001054898,0.0001278521,1.990634e-7,0.0008571841,0.003685351,0.9858394,0.0001041637,0.0003910618,0.007263231],"study_design_scores_gemma":[0.01291728,0.002596447,0.001001893,0.0001980227,0.0004318777,0.00001608373,0.001286608,0.5422019,0.4246608,0.0006654729,0.0126235,0.001400112],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6423026,0.00006849737,0.3554758,0.0001303091,0.0001475,0.001416622,0.00038616,0.00004542112,0.00002709578],"genre_scores_gemma":[0.8032607,0.00002810236,0.1921191,0.0002503867,0.000134179,0.0002928301,0.003790649,0.00004415694,0.00007993957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5611786,"threshold_uncertainty_score":0.9999906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03079255120416373,"score_gpt":0.2834839935097028,"score_spread":0.2526914423055391,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}